80
81
Doğrusal olmayan modellerden birisi piksel içerisindeki karışımın homojen olduğu kabulüdür. Yani ışık küçük boyutlarda birçok yansıma yaptıktan sonra sensöre ulaşmaktadır. Bu kadar fazla yansıma durumunda, karışım probleminin çözümü oldukça zorlaşmaktadır. Genellikle bu modellemede Hapke modeli temel alınarak çalışmalarda uygulanmıştır. Bunun dışında yine destek vektör makineleri, çekirdek metotları, sinir ağları gibi birçok yöntem kullanılmıştır.
Homojen karışımdaki çözümün zor olması ve hesap yükünün fazla olmasından dolayı, araştırmacılar yansıma sayısını en fazla ikiye indirerek yeni bir model kullanmışlardır.
Bu model bilineer modeldir. Bu modeldeki en çok iki yansıma sayısının kabulü, mantıksal olarak çoğu durumda doğru sayılabilir. Çünkü yansıma değerleri (0,1) aralığında olduğundan, bu değerlerin ikiden fazla çarpımı, sonucu sıfıra yaklaştırmakta ve spektral karışımdaki etki miktarının azalmasına neden olmaktadır. Araştırmacılar bu yüzden ikiden fazla yansıma durumunun düşünülmesinin pek gerekli olmadığını düşünmüşlerdir.
Yapılan çalışmalar incelendiğinde, her modellemenin başarılı sonuç ürettiği bir veri dizisi bulmak mümkündür. Tez çalışmasında ise şu ana kadar yapılan çalışmalarda yapılan bazı kabullerin doğru olmadığı vurgulanmakta ve ortaya bir teori konulmaktadır. Literatürde bilineer ve diğer modellerde çok büyük oranda sadece yansıma etkileşiminin dikkate alınması, etkileşim terimlerine eşit ağırlık değeri verilmesi, bolluk değeri toplamının 1’e eşitlenme durumunun sadece doğrusal etkileşim için düşünülmesi, son öğelerin fiziksel varlığı oranında spektral karışıma etki ettiğinin kabul edilmesi, etkileşim spektrumlarının bolluk değerlerinin fiziksel varlık oranına göre ayarlanması, görüntüden piksel seçilerek bu pikselin son öğe spektrumu olarak düşünülerek spektral ayrıştırmada kullanılması gibi durumlar eleştirilmiştir.
Fiziksel anlamda, spektral karışım meydana gelirken, pikseldeki materyaller arasında sadece yansıma etkileşimi meydana gelmez. Bununla birlikte, iletim ve soğurma spektrumları da spektral karışımda çok önemli belirleyici faktörler olarak karşımıza çıkmaktadır. Tezde önerilen model, bilineer modelleme temelinde bütün ikili etkileşimleri dikkate almakta ve karışımı buna göre modellemektedir. Bitki örtüsü
82
sahnelerinde, bitki gelişimiyle birlikte, spektral karışımdaki son öğelerin ve etkileşim spektrumlarının bolluk değerleri de değişmektedir. Örneğin yapraktan doğrudan yansıma ve/veya yapraktan yansıdıktan sonra başka bir yapraktan yansıma oranlarının spektral karışımdaki değerlerinin fazla olması, bitkinin gelişmiş ve büyümüş olduğunu, piksel içinde fazlaca yer kapladığını göstermektedir. Aynı zamanda her bitki çeşidinin bolluk değer değişimi kendine has bir özellik taşımaktadır. Örneğin aynı değerde NDVI üreten mısır ve pamuk görüntü pikseli ayrıştırıldığında, bilineer modeldeki her terimin bolluk değeri bitki çeşidine göre farklılık gösterebilmektedir.
Tezde önerilen yöntem mevcutta literatürdeki doğrusal ve en önemli bilineer modeller ile kestirim hatası bakımından karşılaştırılmıştır. Yöntemin doğrusal modele ve önemli bilineer modellere kestirim hatası anlamında üstünlük sağladığı görülmüştür. Ayrıca önerilen yöntemle bitki örtüsü sınıflaması yapılmıştır. Görüntüde alt piksele düşülen ve spektral karışma oranının çok yüksek olduğu durumlarda oldukça iyi sınıflandırma sonuçları elde edilmiştir.
Geliştirilen yöntemin, gelecekte spektral ayrıştırma konusunda yapılacak çalışmalarda farklı bir pencere açacağı, çalışmalara önemli bir referans kaynağı olacağı değerlendirilmektedir.
83
KAYNAKLAR
Adams, J.B., Sabol, D.E., Kapos, V., Almeida, R., Roberts, D.A., Smith, M.O. and Gillespie, A.R. 1995. Classification of multispectral images based on fractions of endmembers application to land-cover change in the Brazilian amazon.
Remote Sensing of Environment, 52, 137-154.
Almog, O., Shoshany, M. and Alchanatis, V. 2007. Improving Hyperspectral Classification based on Wavelet Decomposition. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol 37, 443-446
Altmann, Y., Halimi, A., Dobigeon, N. and Tourneret, J. 2012. Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery. IEEE Transactions on Image Processing. 21(6), 3017-3025
Anonim. 2012. Web Sitesi: https://www.hvkk.tsk.tr, Erişim Tarihi: 20.05.2018.
Anonim. 2016. Web Sitesi: http://www.cartospace.com.tr/?page_id=20, Erişim Tarihi:
22.05.2018.
Anonymous. 2010. Web Sitesi: https://belspo.be/organisation/Publ/pub_ostc/Th_en.pdf, Erişim Tarihi: 22.05.2018.
Anonymous. 2013. Web Sitesi: https://www.spar3d.com/news/lidar/oil-gas-industry-asks-airborne-remote-sensor-makers-for-help/, Erişim Tarihi: 21.05.2018.
Anonymous. 2014. Web Sitesi: http://rs.geo.tuwien.ac.at/, Erişim Tarihi: 23.05.2018.
Anonymous. 2015. Web Sitesi: https://eros.usgs.gov/doi-remote-sensing- activities/2015/innovation-near-surface-remote-sensing-vegetation-growth-dynamics, Erişim Tarihi: 22.05.2018.
Anonymous. 2017. Web Sitesi: https://www.slideshare.net/OpenMapsLimited/landsat-3385760, Erişim Tarihi: 22.05.2018.
Atkinson, P., Cutler, M. and Lewis, H., 1997. Mapping sub-pixel proportional land cover with AVHRR imagery. International Journal of Remote Sensing. 18(4), 917-935.
Atkinson, P.M. and Lewis, P. 2000. Geostatistical classification for remote sensing: an introduction. Computers & Geosciences. 26, 361-371.
Blanzieri, E., Melgani, F. 2008. Nearest neighbor classification of remote sensing images with the maximal margin principle. IEEE Transactions on Geoscience and Remote Sensing, 46, 1804-1811.
Borel, C., and Gerstl, S. 1994. Nonlinear spectral mixing models for vegetative and soil surfaces, In Journal of Remote Sensing of Environment, 47(3), 403-416.
Chen, X., Chen, J., Jia, X. and Wu, J. 2010. Impact of collinearity on linear and nonlinear spectral mixture analysis. IEEE Workshop on Hyperspectral Image
84
Signal Processing:Evolution on Remote Sensing (WHISPERS). 1-4, Reykjavik, Iceland.
Chen, X., Chen, J., Jia, X., Somers, B., Wu, J. and Coppin, P. 2011. A quantitative analysis of virtual endmembers’ increased impact on the collinearity effect in spectral Unmixing. IEEE Transaction on Geoscience and Remote Sensing.
49(8), 2945- 2956.
Çimtay, Y. ve İlk, H. G. 2017. A Novel Derivative-Based Classification Method for Hyperspectral Data Processing. In Journal of Advances in Electrical and Electronic Engineering, 15(4), 657-662.
Deer, P.J. and Eklund, P. 2003. A Study of Parameter Values for a Mahalanobis Distance Fuzzy Classifier. Fuzzy Sets and Systems. 137, 191-213.
Dhodhi, M.K., Saghri, J.A., Ahmad, I. and Mustafa, R. 1999 D-ISODATA: A Distributed Algorithm for Unsupervised Classification of Remotely Sensed Data on Network of Workstations. Journal of Parallel and Distributed Computing, 59, 280-301.
Dobigeon, N., Tourneret, J., Richard, C., Bermudez, J.C., McLaughlin, S. and Alfred, O. 2013. Nonlinear Unmixing of Hyperspectral Images: Models and Algorithms, Laboratoire de Physique des Solides, CNRS, Univ. Sud, Univ. Paris-Saclay, Orsay Cedex, France.
Dwivedi, R.S., Kandrika, S. and Ramana, K.V. 2004. Comparison of Classifiers of Remote-Sensing Data for Land-Use/Land-Cover Mapping. Current Science. 86, 328-335.
Fan, W., Hu, B. and Miller, J. 2009. Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated-forest hyperspectral data. International Journal of Remote Sensing, 30(11), 2951-2962.
Foody, G.M. 1999. The Continuum of Classification Fuzziness in Thematic Mapping.
Photogrammetric Engineering and Remote Sensing, 65, 443-451.
Fisher, P. 1997. The Pixel: A Snare and a Delusion. International Journal of Remote Sensing, 18, 679-685.
Foody, G.M. and Cox D.P. 1994. Sub-pixel Land Cover Composition Estimation Using a Linear Mixture Model and Fuzzy Membership Functions. International Journal of Remote Sensing. 15, 619-631.
Foody, G. 1996. Relating the land-cover composition of mixed pixels to artificial neural network classification output. Photogrammetric Engineering and Remote Sensing. 62(5), 491–499
Friedl, M.A. and Brodley, C.E. 1997. Decision Tree Classification of Land Cover from Remotely Sensed Data. Remote Sensing of Environment. 61, 399-409.
Gislason, P.O., Benediktsson, J.A. and Sveinsson J.R. 2006. Random Forests for Land Cover Classification. Pattern Recognition Letters. 27, 294-300.
85
Gonçalves, M.L., Netto, M.L.A., Costa J.A.F. and Zullo Júnior J. 2008. An Unsupervised Method of Classifying Remotely Sensed Images using Kohonen Self organizing Maps and Agglomerative Hierarchical Clustering Methods.
International Journal of Remote Sensing, 29, 3171-3207.
Gualtieri, J.A. and Cromp, R.F. 1999. Support Vector Machines for Hyperspectral Remote Sensing Classification, In The 27th AIPR Workshop: Advances in Computer-Assisted Recognition. International Society for Optics and Photonics.
35(84), 221-232.
Halimi, A., Altmann, Y., Dobigeon, N. and Tourneret, J., 2011. Nonlinear Unmixing of Hyperspectral Images Using a Generalized Bilinear Model. IEEE Transactions on Geoscience and Remote Sensing. 49(11), 4153-4162.
Hapke, B. 1993. Theory of Reflectance and Emittance Spectroscopy. Cambridge Univ.
Press, 513, Cambridge.
Heylen, R., Parente, M. and Gader, P. 2014. A Review of Nonlinear Hyperspectral Unmixing Methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6), 1844-1868
Homer, C., Dewitz J., Fry J., Coan, M., Hossain, N., Larson, C., Herold, N., McKerrow, A.,VanDriel, J.N. and Wickham, J. 2007. Completion of the 2001 National Land Cover Database for the Conterminous United States. Journal of Photogrammetric Engineering and Remote Sensing, 73, 337-341.
Hsu, P., and Yang, H. 2007. Hyperspectral Image Classification Using Wavelet Networks. IEEE International Geoscience and Remote Sensing Symposium, IGARSS. 1767-1770, Barcelona, Spain.
Huang C., Davis L.S. and Townshend J.R.G. 2002. An Assessment of Support Vector Machines for Land Cover Classification. International Journal of Remote Sensing. 23, 725-749.
Huete, A., Jackson, R. and Post, D. 1985. Spectral response of a plant canopy with different soil backgrounds. Journal of Remote Sensing of Environment. 17(1), 37–53
Ishibuchi, H., Nozaki, K., Yamamoto, N. and Tanaka, H. 1994. Construction of Fuzzy Classification Systems with Rectangular Fuzzy Rules using Genetic Algorithms.
Fuzzy Sets and Systems. 65, 237-253.
Jensen, J.R. 2009. Remote Sensing of the Environment: An Earth Resource Perspective 2/e. Pearson Education, India.
Jiang H., Zhao, D., Cai, Y. and An, S. 2012. A Method for Application of Classification Tree Models to Map Aquatic Vegetation using Remotely Sensed Images from Different Sensors and Dates. Sensors. 12, 12437-12454.
Kavzoğlu, T. 2016. Uzaktan algılama teknolojisi notları, Gebze Yüksek Teknoloji Enstitüsü, Gebze, Kocaeli.
86
Kavzoglu, T. and Mather, P.M. 2003. The Use of Backpropagating Artificial Neural Networks in Land Cover Classification. International Journal of Remote Sensing. 24, 4907-4938.
Kulkarni, A.D. and Kamlesh, L. 1999. Fuzzy Neural Network Models for Supervised Classification: Multispectral Image Analysis. Geocarto International. 4, 42-51.
Li, J. 2004. Wavelet-Based Feature Extraction for Improved Endmember Abundance Estimation in Linear Unmixing of Hyperspectral Signals. IEEE International Geoscience and Remote Sensing Symposium, Vol 42, 644-649, Anchorage, AK, USA.
Li, J., Li, X., Huang, B. and Zhao, L. 2016. Hopfield Neural Network Approach for Supervised Nonlinear Spectral Unmixing, IEEE Geoscience and Remote Sensing Letters, 13(7), 3340-3350.
Li,Y. 2002. Linear Unmixing of Hyperspectral Signals via Wavelet Feature Extraction.
Doktora Tezi, Mississippi State University, Electrical and Computer Engineering, 167, Mississippi.
Licciardi, G. and Frate, F. 2010. A Neural Network Approach For Pixel Unmixing In Hyperspectral Data. IEEE 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), Reykjavik, Iceland.
Licciardi, G. and Frate, F. 2011. Pixel Unmixing in Hyperspectral Data by Means of Neural Networks. IEEE Transactions On Geoscience And Remote Sensing.
49(11), 4163-4172.
Lillesand, T.M., Kiefer, R.W. and Chipman, J.W. 2004. Remote Sensing and Image Interpretation. Ed. 5. John Wiley & Sons Ltd.
Lu, D. and Weng, Q. 2007. Survey of Image Classification Methods and Techniques for Improving Classification Performance. International Journal of Remote Sensing, 28, 823-870.
Lvovsky, A.I. 2013. Fresnel Equations. Department of Physics and Astronomy. Taylor and Francis: Newyork, Published Online.
Mannan, B. and Ray, A.K. 2003. Crisp and Fuzzy Competitive Learning Networks for Supervised Classification of Multispectral IRS Scenes. International Journal of Remote Sensing. 24, 3491-3502.
Marcelo, J.S. and Paulo, C. 2013. Laws of reflection and Snell’s Law revisited by Video Modeling. 12th Education and Training in Optics and Photonics Conference.
Vol:92(89).
Marconcini, M., Camps-Valls, G. and Bruzzone, L. 2009. A Composite Semisupervised SVM for Classification of Hyperspectral Images. IEEE Geoscience and Remote Sensing Letters. 6, 234-238.
McIver, D.K. and Friedl, M.A. 2002. Using Prior Probabilities in Decision-tree Classification of Remotely Sensed Data. Remote Sensing of Environment. 81, 253-261.
87
Mitraka, Z., Frate, F. and Carbobe, F. 2015. Spectral unmixing of urban Landsat imagery by means of neural Networks. Joint Urban Remote Sensing Event, JURSE.
Mitraka, Z., Frate, F. and Carbobe, F. 2016. Nonlinear Spectral Unmixing of Landsat Imagery for Urban Surface Cover Mapping, Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(9), 3340-3350.
Meganem, I., Deliot, P., Briottet, X., Deville, Y. and Hosseini, S. 2014. Linear-quadratic mixing model for reflectances in urban environments. IEEE Transactions on Geoscience and Remote Sensing, 52(1), 544-558.
Musaoğlu, N. 2014. Uzaktan Algılama Eğitim notları, İTÜ İnşaat Fakültesi, 77s, İstanbul.
Nascimento, J. and Bioucas-Dias, J. 2009. Nonlinear mixture model for hyperspectral Unmixing. Proc. Soc. Photo-Opt. Instrum. Eng. (SPIE), Image Signal Process.
Remote Sensing. Vol 15, 7477
Nguyen, V. and Hakil, K. 2009. Noisy Band Removal Using Band Correlation in Hyperspectral Images. In Korean Journal of Remote Sensing, 25, 263-270.
Pal, M. and Mather, P.M. 2005. Support Vector Machines for Classification in Remote Sensing. International Journal of Remote Sensing. 26, 1007-1011.
Perakis, K., Kyrimis, K. and Kungolos, A. 2000. Monitoring Land Cover Change Detection with Remote Sensing Methods in Magnesia Prefecture in Greece.
Fresenius Environmental Bulletin. 9, 659-666.
Plaza, A., Plaza, R. and Martinez, P. 2008. Joint linear/nonlinear spectral unmixing of hyperspectral image data. IEEE International Geoscience Remote Sensing Symposium. (IGARSS). 4037–4040, Barcelona, Spain.
Puletti, N., Perria, R. and Storchi, P. 2014. Unsupervised classification of very high remotely sensed images for grapevine rows detection. European Journal of Remote Sensing, 47, 45-54.
Ray, T. and Murray, B. 1996. Nonlinear spectral mixing in desert vegetation. Journal of Remote Sensing of Environment. 55(1), 59–64
Roberts, D., Smith, M. and Adams, J. 1993. Green vegetation, nonphotosynthetic vegetation, and soils in AVIRIS data. In Journal of Remote Sensing of Environment, 44(2-3), 255-269.
Roberts, D.A., Gardner, M., Church, R., Ustin, S., Scheer, G. and Green, R.O. 1998.
Mapping Chaparral in the Santa Monica Mountains using Multiple Endmember Spectral Mixture Models. Remote Sensing of Environment. 65, 267-279.
Rollet, R., Benie, G.B., Li, W., Wang, S. and Boucher, J.M. 1998. Image Classification Algorithm based on the RBF Neural Network and K-means. International Journal of Remote Sensing, 19, 3003-3009.
88
Settle, J.J. and Briggs, S.A. 1987. Fast Maximum-likelihood Classification of Remotely Sensed Imagery. International Journal of Remote Sensing. 8, 723-734.
Shalaby, A. and Tateishi, R. 2007. Remote Sensing and GIS for Mapping and Monitoring Land Cover and Land-use Changes in the Northwestern Coastal Zone of Egypt. Applied Geography. 27, 28-41.
Shanmugam, P., Ahn, Y.H. and Sanjeevi, S. 2006. A Comparison of the Classification of Wetland Characteristics by Linear Spectral Mixture Modelling and Traditional Hard Classifiers on Multispectral Remotely Sensed Imagery in Southern India. Ecological Modelling. 194, 379-394.
Stefan, A. 2010. Band reduction for hyperspectral imagery processing. In Proc. SPIE 7533 Computational Imaging VIII, Vol 7533, San Jose, California.
Sun, W., Jiang, M., Li, W. and Liu, Y. 2016. A Symmetric Sparse Representation Based Band Selection Method for Hyperspectral Imagery Classification. In Journal of Remote Sensing. 8(3), 238-254.
Tseng, M.H., Chen, S.J., Hwang, G.H. and Shen, M.Y. 2008. A Genetic Algorithm Rule- based Approach for Land-cover Classification. ISPRS Journal of Photogrammetry and Remote Sensing. 63, 202-212.
Woodcock, C.E. and Gopal, S. 2000. Fuzzy Set Theory and Thematic Maps: Accuracy Assessment and Area Estimation. International Journal of Geographical Information Science. 14, 153-172.
Wu, C. and Murray, A.T. 2003. Estimating Impervious Surface Distribution by Spectral Mixture Analysis. Remote Sensing of Environment. 84, 493-505.
Wu, C. 2004. Normalized Spectral Mixture Analysis for Monitoring Urban Composition using ETM+ Imagery. Remote Sensing of Environment. 93, 480-492.
Xian, G. and Crane, M. 2005. Assessments of Urban Growth in the Tampa Bay Watershed using Remote Sensing Data. Remote Sensing of Environment. 97, 203-215.
Xu, M., Watanachaturaporn, P., Varshney, P. and Arora, M. 2005. Decision Tree Regression for Soft Classification of Remote Sensing Data. Remote Sensing of Environment, 97, 322-336.
Yang, X. and Liu, Z. 2005. Use of Satellite-derived Landscape Imperviousness Index to Characterize Urban Spatial Growth. Computers, Environment, and Urban Systems. 29, 524-540
Yuan, F., Sawaya, K.E., Loeffelholz, B.C. and Bauer, M.E. 2005. Land Cover Classification and Change Analysis of the Twin Cities (Minnesota) Metropolitan Area by Multitemporal Landsat Remote Sensing. Remote Sensing of Environment. 98, 317-328.
Zhang, J. and Foody, G.M. 1998. A Fuzzy Classification of Sub-urban Land Cover from Remotely Sensed Imagery. International Journal of Remote Sensing. 19, 2721-2738.
89
Zhang, L., Li, D., Tong, Q. and Zheng, L. 1998. Study of the spectral mixture model of soil and vegetation in PoYang Lake area, China. International Journal of Remote Sensing, 19(11), 2077-2084.
Zhu, H.W. and Basir O. 2005. An Adaptive Fuzzy Evidential Nearest Neighbor Formulation for Classifying Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 43, 1874-1889.
90